Tweet

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @rappa753

Albert Rapp

@rappa753

May 31

Data cleaning is tedious.

But it's much easier with the {janitor} package. Especially if you work with Excel files.

Here are 5 underrated features from {janitor}. #rstats

1 // Create clean names

This is absolutely the best function. It transforms column names such that they are easier to use for programming.

Left: Bad for programming
Right: Good for programming

2 // Remove empty or constant cells from Excel files

Excel files can be messy to read in R. Lots of weird column names and empty cells.

{janitor} takes care of that for us.

Read 8 tweets

Albert Rapp

@rappa753

May 19

Ever heard of logistic regression? Or Poisson regression? Both are generalized linear models (GLMs).

They're versatile statistical models. And by now, they've probably been reframed as super hot #MachineLearning.

Brush up on their math with this thread. #rstats

Let's start with logistic regression. Assume you want to classify a penguin as male or female based on its

* weight,
* species and
* bill length

Better yet, let's make this specific. Here's a dataviz for this exact scenario. It is based on the {palmerpenguins} data set.

As you can see, the male and female penguins form clusters that do not overlap too much.

However, regular linear regression (LR) won't help us to distinguish them. Think about it. Its output is something numerical. Here, we want to find classes.

Read 26 tweets

Albert Rapp

@rappa753

May 12

The best way to learn data analysis is to actually practice it.

Each week, the #tidyTuesday challenge gives you plenty of opportunity for this.

Don't know how to get started with the challenge? In case you missed it, I've put together an #rstats guide in January.

First, get the data.

Head over to the tidyTuesday's GitHub repo at github.com/rfordatascienc…

Just copy the code from the "Get the data" section.

Next, I suggest that you use the clean_names() function from the {janitor} package.

This will format the column names of your data set so that it's easier to work with.

Huge time saver!

Read 24 tweets

Albert Rapp

@rappa753

May 5

@infobeautiful

I used to think tables are boring.

But they can be beautiful & engaging.

Here's a nice example from @infobeautiful.

It uses many eye-catching elements but you don't need them to create a great table.

Just stick to these guidelines 🧵#dataviz

Let's start with a not so great table and improve it.

Here's a table I would have created just a few months ago.

Not so sexy, right? Let's clean that up.

1. Avoid vertical lines

The above table uses waaaay to many grid lines.

Without vertical lines, the table will look less cramped.

Have a look for yourself.

Read 16 tweets

Albert Rapp

@rappa753

Apr 28

I hate code duplication. It's just a sure way to bloat code and do copy-and-paste mistakes 🙈

In Shiny, modules help me to avoid that.

BONUS: They move the app's logic to separate + reusable functions for cleaner code.

Here's how modules work. #rstats

Let's build an app that displays a scatterplot of two variables of a given data set.

Let's imagine that each data set needs its own page in our app. Here's how that could look.

Every element of our app will need to get a unique ID. And we will need to repeat that for every data set.

For two data sets a non-modularized Shiny UI could look something like this.

Notice how I have to append "_iris" each time for the second tabPanel / data set.

Read 11 tweets

Albert Rapp

@rappa753

Apr 4

Paired bar charts suck at comparing values. The only reason they're used all the time is because they are easy to create.

But there are better alternatives that are just as easy.

Here's how to create 4 better alternatives with #rstats.

0 // Where's the code?

The code for all plots can be found at albert-rapp.de/posts/ggplot2-…

This thread walks you through the code quickly.

1 // Dot plot

Instead of using bars next to each other, why not points on the same line?

Makes comparison suuper easy.

And it takes only a geom_point() layer. Dead-simple, right?

I think it's even easier to create than a paired bar chart.

Read 15 tweets

Share this page!

Enter Twitter Thread URL to Unroll

Albert Rapp

People who liked this thread also liked...

Try unrolling a thread yourself!

More from @rappa753

Albert Rapp

Albert Rapp

Albert Rapp

Albert Rapp

Albert Rapp

Albert Rapp

Did Thread Reader help you today?

Don't want to be a Premium member but still want to support us?

Send Email!